(108 days)
The Spectral MD DeepView system is intended for studies of blood flow in the microcirculation. The DeepView system is suitable for a wide variety of clinical applications including plastic surgery, diabetes, dermatology, vascular surgery, wound healing, neurology, physiology, neurosurgery and anesthetics.
Deep View system-based technology combines real-time digital analysis of optical signatures, thereby sensitizing an imager to photon-tissue interactions deep below the skin's surface. These image signatures are unique to the body and relate directly to a person's dynamic nature - both in terms of the quantity and quality of important physiological properties. This technology is non-invasive and uses no harmful radiation such as X-rays and allows clinical investigators to look deeper into the body, delivering images of blood flow under the skin's surface without ever touching the patient.
The DeepView system is composed of a mobile cart with uninterruptible power supply, a laptop computer with remote multimedia keyboard, an LCD screen mounted on a bracket that allows for side-to-side panning, a mechanical arm, a CMOS camera with DSP electronics, and disposable LED cartridges with an associated LED driver control board.
The provided document describes the DeepView Digital Video Physiological Portable Imaging System, a device intended for studies of blood flow in the microcirculation. It focuses on demonstrating substantial equivalence to predicate devices rather than establishing novel acceptance criteria and proving performance against them in a de novo study.
Here's an analysis based on the available information:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly define acceptance criteria in terms of specific performance metrics (e.g., sensitivity, specificity, accuracy, or quantitative blood flow measurements) that the DeepView device needed to meet. Instead, the study's goal was to demonstrate substantial equivalence to existing predicate devices.
| Acceptance Criterion (Implicit) | Reported Device Performance |
|---|---|
| Ability to detect blood flow optically | DeepView uses optical methods to detect blood flow and pulse pressure. |
| Ability to detect pulse frequency | DeepView was tested alongside predicate devices to show substantial equivalence in detecting pulse frequency. |
| Ability to produce flow images | DeepView displays 2D color images demonstrating relative blood flow, similar to moorLDI and moorLDI2-IR. |
| No new issues of safety and efficacy compared to predicate devices | Comparison testing conducted demonstrates that the DeepView is substantially equivalent and does not introduce any new issues of safety and efficacy. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: Not specified. The document mentions "comparison testing" which included "camera distance testing and tissue phantom testing." This implies the use of a controlled test environment (tissue phantoms) rather than human subjects. No specific number of phantoms or test cases is provided.
- Data Provenance: The testing appears to be conducted in a laboratory setting using "tissue phantoms." There is no mention of human data, country of origin, or whether it was retrospective or prospective.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
Not applicable in the context of this submission. The ground truth for the comparison testing seems to be the performance of the predicate devices themselves, as the DeepView's output was compared to theirs. There's no indication of independent expert review to establish a separate "ground truth" for the test set.
4. Adjudication Method for the Test Set
Not applicable. There is no mention of human-in-the-loop assessment or expert adjudication for the "comparison testing." The comparison was against the output of the predicate devices.
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was Done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
No, an MRMC comparative effectiveness study involving human readers and AI assistance was not conducted or reported. This submission focuses on the standalone device's equivalence to existing technology, not on improving human reader performance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done
Yes, the testing described appears to be a standalone performance evaluation of the DeepView device against the predicate devices. The "comparison testing" suggests the DeepView's output was directly compared to the outputs of the moorLDI, moorLDI2-IR, and Avant 9600. The device's ability to "detect blood flow and pulse pressure" and produce "2D color images of relative perfusion distribution" constitutes its standalone performance.
7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)
The "ground truth" for the comparison testing was effectively the performance of the predicate devices. The DeepView was evaluated for its ability to produce similar results (detect blood flow, pulse frequency, and produce flow images) to the already legally marketed and accepted predicate devices (moorLDI, moorLDI2-IR, and Avant 9600). For the tissue phantom testing, the "ground truth" would implicitly be the known properties of the phantoms and the expected measurements, as validated by the predicate devices.
8. The Sample Size for the Training Set
Not applicable. As this is a 510(k) premarket notification for a device using established optical principles, there is no mention of an "AI algorithm" requiring a training set in the contemporary sense. The device's operation is based on "real-time digital analysis of optical signatures" and "non contact Photoplethysmography (PPG)," which points to signal processing rather than machine learning models that require training data.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as there is no mention of a training set or an AI algorithm that would require one.
§ 870.2120 Extravascular blood flow probe.
(a)
Identification. An extravascular blood flow probe is an extravascular ultrasonic or electromagnetic probe used in conjunction with a blood flowmeter to measure blood flow in a chamber or vessel.(b)
Classification. Class II (performance standards).